00:21:09 <jbk> as opposed to the classic Dewey, Cheatham, and Howe
20:00:59 <jbk> ok.. this is interesting.. even on the CX-5 cards, reading MLXCX_REG_PCAM failes with MLXCX_CMD_R_BAD_SYS_STATE
20:01:06 <jbk> at least the ones in this system
20:02:50 <richlowe> w
20:02:53 <richlowe> oops
20:39:37 <Smithx10> Anyone use or Check out https://github.com/FDio/vpp ?
20:40:52 <Smithx10> Ahh nevermind it’s another kernel bypass thingie
20:41:03 <tsoome_> is src.iluumos.org very busy or is it my network....
20:41:28 <tsoome_> got 504 gateway timeout  from it...
20:41:51 <tsoome_> src.illumos.org even :)
20:42:23 <richlowe> it works here, but sometimes it stalls on people
20:43:01 <richlowe> (it works when I spell it right.  Did you?)
20:43:07 <tsoome_> :)
20:43:38 <tsoome_> i better kick my router just in case...
20:50:50 <tsoome_> so, mdb ::mutex command will print put info about mutex, the held pointer there is pointer to kthread_t?  and to get the stack trace, I can just use that pointer with ::stacks ? 
20:52:34 <jbk> ::stack (no s)
20:52:48 <jbk> ::stacks does something different
20:52:55 <rmustacc> I usually use ::findstack -v
20:53:04 <jbk> err yeah
21:07:29 <tsoome_> so, UTM with cores > 1 usually will hung on boot. so I found thread with start_cpu() in its stack and wanted to check the mutex and found this https://paste.ec/paste/sG5kZxnU#rzagv9Op+ifRrqGXUfLVXgmP8HFksN9tAm8Cwa1D4c8  -- as much as I can see, cpus should be cpuset_t in data segment and swtch_from_zombie() should be busy with resume_from_zombie() 
21:08:23 <tsoome_> not really sure if that start_cpu() really is guilty one, but found this example to be interesting....
21:09:24 <tsoome_> ofc course resume_from_zombie() does some things with stack... 
21:09:45 <richlowe> ::stack doesn't take a kthread_t
21:09:55 <richlowe> ::findstack does, ::stacks also does I think
21:10:21 <tsoome_> yes it does.
21:10:35 <tsoome_> stacks and findstack agree there
21:10:48 <richlowe> ::stack/$C take a frame pointer
21:23:41 <richlowe> does anyone know of a debugger that visualizes the stack and annotates it with the %pc when %sp was adjusted?
21:23:49 <richlowe> (read %rip/%rsp/%rbp if you'd like)
21:24:03 <richlowe> I haven't used a debugger that had anything approaching a gui since DDD in the 90s
21:24:42 <richlowe> that is the actual _stack_ not a stack trace.  I'm basically asking for $C but with the data between each %fp ::dump'd
21:25:29 <richlowe> (it feels like with dwarf you could make that substantially less grody, which is why I'm asking)
21:25:34 <tsoome_> have you checked this one: https://github.com/cyrus-and/gdb-dashboard -- altho I'm not sure it can do what you are asking for:D
21:27:02 <richlowe> gosh that's busy.  It might help though!
21:27:28 <tsoome_> I have found it useful sometimes....
22:05:11 <tsoome_> hm, boot -B smt_enabled=false and no hung...
22:09:49 <tsoome_> tested smt_enabled=false because of this: https://paste.ec/paste/Fy63rJu4#VMxs9xHP49Om+8iMZbH-ZJwuTD6Nch1T8Dp1TKGEjCk  
22:38:06 <tsoome_> hm, apparently no, it was just  one of random good boot..